In order to solve the dilemma that particle swarm optimization (PSO) cannot well balance the exploration and exploitation, a density peak based multi subpopulation particle swarm optimization algorithm is proposed with dimensionally reset strategy (DPMPSO). In the proposed DPMPSO, the idea of relative distance originated from density peak clustering is firstly adopted and then it is combined with the fitness value of particles to divide the whole swarm into two subpopulations: the top subpopulation and the bottom subpopulation. Secondly, the learning strategy is designed, focusing on local search for the top subpopulation and the learning strategy paying more attention to global search for the bottom subpopulation, which can well balance the exploration and exploitation. Finally, particles that fall into local optima will be reset by crossover with the global optima dimensionally, which can not only effectively avoid premature but also significantly reduce invalid iteration. The experiment results on 10 benchmark problems and CEC2017 optimization problems demonstrate that DPMPSO performs better than some representative PSOs and other optimization algorithms with significant difference.